Raw API

Direct HTTP against the OpenAI-compatible endpoint. Works with any language.

Overview

The base URL is https://api.beansai.dev/v1. Authenticate with a Bearer token in theAuthorization header. Endpoints mirror OpenAI:

POST /chat/completions — chat, streaming, tool calling
GET /models — list available models

curl

shell

curl https://api.beansai.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-beans-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ],
    "stream": false
  }'

Basic usage

Use the official OpenAI SDKs and just swap the base URL.

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-beans-...",
    base_url="https://api.beansai.dev/v1",
)

res = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(res.choices[0].message.content)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-beans-...",
  baseURL: "https://api.beansai.dev/v1",
});

const res = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(res.choices[0]?.message?.content);

Streaming

shell

curl https://api.beansai.dev/v1/chat/completions \
  -N \
  -H "Authorization: Bearer sk-beans-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "Count to 5"}],
    "stream": true
  }'

SSE events follow the data: {json}\n\n format; final event is data: [DONE].

List models

shell

curl https://api.beansai.dev/v1/models \
  -H "Authorization: Bearer sk-beans-..."

Tips

Rate limits are per-key and returned in X-RateLimit-* headers.
On 429 or 5xx, retry with exponential backoff. BeansAI's load balancer will pick a healthy upstream.
Cost per request is returned in X-Request-Cost-Micro-Usd. Great for real-time billing UIs.

curl https://api.beansai.dev/v1/chat/completions \ -H "Authorization: Bearer sk-beans-..." \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.5", "messages": [ {"role": "user", "content": "Hello, world!"} ], "stream": false }'

Basic usage

Use the official OpenAI SDKs and just swap the base URL.

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-beans-...",
    base_url="https://api.beansai.dev/v1",
)

res = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(res.choices[0].message.content)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-beans-...",
  baseURL: "https://api.beansai.dev/v1",
});

const res = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(res.choices[0]?.message?.content);

Streaming

shell

curl https://api.beansai.dev/v1/chat/completions \
  -N \
  -H "Authorization: Bearer sk-beans-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "Count to 5"}],
    "stream": true
  }'

SSE events follow the data: {json}\n\n format; final event is data: [DONE].